TRAINING A DEEP NEURAL NETWORK MODEL TO GENERATE RICH OBJECT-CENTRIC EMBEDDINGS OF ROBOTIC VISION DATA

Training a machine learning model (e.g., a neural network model such as a convolutional neural network (CNN) model) so that, when trained, the model can be utilized in processing vision data (e.g., from a vision component of a robot), that captures an object, to generate a rich object-centric embedd...

Full description

Saved in:
Bibliographic Details
Main Authors PIRK, Soeren, LYNCH, Harrison, BAI, Yunfei, KHANSARI ZADEH, Seyed Mohammad, SERMANET, Pierre
Format Patent
LanguageEnglish
French
Published 02.04.2020
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Training a machine learning model (e.g., a neural network model such as a convolutional neural network (CNN) model) so that, when trained, the model can be utilized in processing vision data (e.g., from a vision component of a robot), that captures an object, to generate a rich object-centric embedding for the vision data. The generated embedding can enable differentiation of even subtle variations of attributes of the object captured by the vision data. L'invention concerne l'entraînement d'un modèle d'apprentissage machine (par exemple, un modèle de réseau neuronal tel qu'un modèle de réseau neuronal convolutif (CNN)) de telle sorte que, lorsqu'il est entraîné, le modèle peut être utilisé dans le traitement des données de vision (par exemple, à partir d'un composant de vision d'un robot), qui capturent un objet, pour générer une riche incorporation centrée sur un objet pour les données de vision. L'incorporation générée peut permettre la différenciation de variations, même subtiles, d'attributs de l'objet capturé par les données de vision.
AbstractList Training a machine learning model (e.g., a neural network model such as a convolutional neural network (CNN) model) so that, when trained, the model can be utilized in processing vision data (e.g., from a vision component of a robot), that captures an object, to generate a rich object-centric embedding for the vision data. The generated embedding can enable differentiation of even subtle variations of attributes of the object captured by the vision data. L'invention concerne l'entraînement d'un modèle d'apprentissage machine (par exemple, un modèle de réseau neuronal tel qu'un modèle de réseau neuronal convolutif (CNN)) de telle sorte que, lorsqu'il est entraîné, le modèle peut être utilisé dans le traitement des données de vision (par exemple, à partir d'un composant de vision d'un robot), qui capturent un objet, pour générer une riche incorporation centrée sur un objet pour les données de vision. L'incorporation générée peut permettre la différenciation de variations, même subtiles, d'attributs de l'objet capturé par les données de vision.
Author KHANSARI ZADEH, Seyed Mohammad
LYNCH, Harrison
SERMANET, Pierre
BAI, Yunfei
PIRK, Soeren
Author_xml – fullname: PIRK, Soeren
– fullname: LYNCH, Harrison
– fullname: BAI, Yunfei
– fullname: KHANSARI ZADEH, Seyed Mohammad
– fullname: SERMANET, Pierre
BookMark eNqNjM0KgkAURl3Uor93uNBaMIXC5Thz1SmdG-MtlyIxrkIFe3-aRQ_Q6vAdPs42WI3T6DbBwFZoo00BAhTiHQw-rKg8uCV7g5oUVsAEBRq0ghGsliVQdkXJoUTDfgPWGSrlKw1QDpYyYm-futFkQAkW-2A99O_FHX7cBcccWZahm6fOLXP_cqP7dC3FURxF5zS5pOKU_Pf6AqQRN08
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
DocumentTitleAlternate ENTRAÎNEMENT D'UN MODÈLE DE RÉSEAU NEURONAL PROFOND POUR GÉNÉRER DE RICHES INCORPORATIONS CENTRÉES SUR DES OBJETS DE DONNÉES DE VISION ROBOTIQUE
ExternalDocumentID WO2020069379A1
GroupedDBID EVB
ID FETCH-epo_espacenet_WO2020069379A13
IEDL.DBID EVB
IngestDate Fri Jul 19 12:56:08 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
French
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_WO2020069379A13
Notes Application Number: WO2019US53554
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200402&DB=EPODOC&CC=WO&NR=2020069379A1
ParticipantIDs epo_espacenet_WO2020069379A1
PublicationCentury 2000
PublicationDate 20200402
PublicationDateYYYYMMDD 2020-04-02
PublicationDate_xml – month: 04
  year: 2020
  text: 20200402
  day: 02
PublicationDecade 2020
PublicationYear 2020
RelatedCompanies GOOGLE LLC
RelatedCompanies_xml – name: GOOGLE LLC
Score 3.2568364
Snippet Training a machine learning model (e.g., a neural network model such as a convolutional neural network (CNN) model) so that, when trained, the model can be...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTING
COUNTING
PHYSICS
Title TRAINING A DEEP NEURAL NETWORK MODEL TO GENERATE RICH OBJECT-CENTRIC EMBEDDINGS OF ROBOTIC VISION DATA
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200402&DB=EPODOC&locale=&CC=WO&NR=2020069379A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfR1dT8Iw8ELw801R4weaJpq9LeIYgz0Qs62dTNlKZvl4I2xsiYkBIjP-fa8FlCee2l6TS3vN9T56dwV4MKSMTDNLb0xaE93MsNeyaqlut0yZeDmdNFPpGggjq9M3X0eNUQk-N7kwqk7ojyqOiByVIr8X6r5e_DuxqIqtXD4mHwiaP_uiTbW1dSyPvGZo1G2zHqfc0zwP7TYtildzFspi20FbaQ8V6abkBzZwZV7KYluo-Cew30N8s-IUStmsAkfe5u-1ChyG6yfvChyoGM10icA1Hy7PIBexE0RB9EIcQhnrkYj1Y6eLjRjy-I2EnLIuEZysItMEI3HgdQhXn5voHosEjgkLXUYpYnkn3Ccxd7lA6CCQ9yuhjnDO4d5nwuvouPTxH6XGQ769z_oFlGfzWXYJpCYTVrMkQX3GNpN6bqNWYNhoHeTT5Mkw8iuo7sJ0vXv6Bo7lUAW0GFUoF1_f2S3K6iK5UyT-BWDtjVQ
link.rule.ids 230,309,783,888,25576,76876
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfR1dT8IwsCF-4Zuixg_UJpq9LeIYgz0Qs62dm2wrmeXjjbCxJSZmEJnx73stoDzx1PYuufQj17tr7wOhR03IyDQz1Na0M1X1DHodo5GqZkcXgZezaTsVTwNhZHgD_W3cGlfQ5yYWRuYJ_ZHJEYGjUuD3Ut7Xi_9HLCJ9K5dPyQeA5i8u7xJlbR2LI29oCrG7tM8IcxTHAbtNieIVzgBZbFpgK-2Dkt0W_ECHtohLWWwLFfcEHfSBXlGeokpW1FDV2dReq6GjcP3lXUOH0kczXQJwzYfLM5Tz2PIjP3rFFiaU9nFEB7EVQMNHLO7hkBEaYM7wyjONUxz7joeZLG6iOjTiMMY0tCkhQOUdMxfHzGYcoENf3K-YWNw6Rw8u5Y6nwtQnfzs1GbHtdTYv0F4xL7JLhBsiYDVLEtBnTD1p5iZoBZoJ1kE-S541Lb9C9V2Urnej71HV42EwCfyod4OOBUo6t2h1tFd-fWe3ILfL5E5u9y8vl5BH
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=TRAINING+A+DEEP+NEURAL+NETWORK+MODEL+TO+GENERATE+RICH+OBJECT-CENTRIC+EMBEDDINGS+OF+ROBOTIC+VISION+DATA&rft.inventor=PIRK%2C+Soeren&rft.inventor=LYNCH%2C+Harrison&rft.inventor=BAI%2C+Yunfei&rft.inventor=KHANSARI+ZADEH%2C+Seyed+Mohammad&rft.inventor=SERMANET%2C+Pierre&rft.date=2020-04-02&rft.externalDBID=A1&rft.externalDocID=WO2020069379A1